← Model list
Sarvam 105B
sarvam·sarvam/sarvam-105b·GA·Open weights·sarvam series
Flagship Indian-language reasoning model for enterprise multilingual applications
At a glance
Official pricePrice undisclosed
Lowest paid$0.04 / $0.16
FastRouter Gateway · 1.1× spread
Context131,072
Output limit131,072
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff—
Released / updated2025-09-01 / 2025-09-01
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier high
Intelligence11.9
Value170
Coding—
Agentic—
Output speed—
TTFT—
Value formulaIQ 11.9 ÷ min blended $0.070 = 170
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 3 providers2 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| FastRouter | Gateway | $0.04 | $0.16 | — | — | 131,072 | 131,072 | |
| NanoGPT | Gateway | $0.045 | $0.177 | $0.028 | — | 131,072 | 4,096 | |
| Sarvam AIOfficial | First-party | — | — | — | — | 131,072 | 131,072 | hostTable.undisclosed |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1NanoGPT$15.81
2FastRouter$16.00
The cheapest paid channel is the only channel.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
effort = loweffort = mediumeffort = higheffort = null
1 / 3 providers expose no reasoning control (reasoning_options: []).
Related models
Price historyone sample accumulated per data sync
Input listOutput listMin blended